Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dice rolls and probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పొ
    0.43
    abhave
    0.41
    wString
    0.39
     lebt
    0.38
     Schur
    0.38
     گلوکار
    0.37
    acariy
    0.37
    Tier
    0.37
    ouwd
    0.37
    tier
    0.37
    POSITIVE LOGITS
     dice
    1.77
    Dice
    1.55
     Dice
    1.53
    dice
    1.45
    骰
    1.41
     dices
    1.33
     DICE
    1.18
    🎲
    1.06
     rolls
    1.05
     rolled
    1.02
    Act Density 0.027%

    No Known Activations